sutro-sh/jev-align
Build calibrated AI Functions from human feedback using Jev and GEPA.
From the publisher
README & documentation
Source previewRead the project’s overview, installation instructions and usage examples. The original README is the source of truth.
jev-align is an experimental CLI from Sutro for building AI Functions with TypeSafe's Jev. It finds uncertain examples, asks you to label them, and uses GEPA to improve the function. Use it in your application and keep learning from production examples. https://github.com/user-attachments/assets/81650587-e3f1-4655-8213-ed5f6e120e9a Requires Python 3.11 or newer. Start the CLI with either jeva or jev-align. Use pip install jev-align if you do not use uv. The guided setup discovers local CSV, Parquet, and JSONL files and includes three ready-to-run examples. Each round: Every label comes from you. A higher training score never accepts a proposal automatically. The guided Advanced menu configures: By default, jev-align uses the first 1,000 rows—or the entire dataset when it is smaller—and lets you concatenate all fields or select specific columns. Everything can also be configured with flags: Use repeated --class "NAME=DESCRIPTION" options for multiclass or multilabel tasks, and repeated --score-level options for scoring tasks. Run…
Read the full README ↗ · Preview checked 2026-09-20T08:32:42.305Z
Inside the original README — Document outline
- jev-align
- Demo
- Quick start
- How it works
- Task types
- Configuration
- Jev providers
- Reflection models
- Controls
- Saved AI Functions
- Keep learning from production
- Using a coding agent
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the README
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
Documentation belongs to its respective authors. Reported project/model license: Apache-2.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
What this repository does
Build calibrated AI Functions from human feedback using Jev and GEPA.
Repository facts
- Owner
- sutro-sh
- Primary language
- Python
- Stars
- 249
- Forks
- 19
- Open issues + pull requests
- 1
- License
- Apache-2.0
- Archived
- No
- Default branch
- main
- Created
- 2026-09-19T02:12:23.000Z
- Last push
- 2026-09-20T20:50:08.000Z
Topics and intended use
Owner-supplied topics: active-learning, classification, cli, gepa, human-in-the-loop, jev, prompt-optimization, typesafe-ai
Review the README for scope, installation, examples and limitations. We do not run repository code or certify it.
Evaluate before installing
Review licensing and dependencies, inspect recent commits and unresolved issues, and test in an isolated environment before production use. Stars and forks alone cannot answer these questions.
Source and freshness
Source: GitHub. Metadata observed 2026-09-21T06:41:42.808Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.
Related repositories
EbookFoundation/free-programming-books
donnemartin/system-design-primer